AI test that worked on a scam bot, or someone who doesn’t speak English well: In the novel Blindsight, they’re discussing whether an alien they’ve encountered is sentient, so the linguist sends this message:
“Our cousins lie about the family tree, with nieces and nephews and Neanderthals. We do not like annoying cousins.”
“We’d like to know about this tree.”
Sascha muted the channel and gave us a look that said Could it be any more obvious? “It couldn’t have parsed that. There were three linguistic ambiguities in there. It just ignored them.”
The scammer ignored this and ChatGPT whiffed it. Claude gave a similar response in that it tried to explain a sentence that can’t possibly be explained. Neither caught the ambiguities. Happy hunting!
Came back to this post catch any new comments or ideas.
How the hell have you not finished Echopraxia?! It’s not as good, but it’s still a banger, and it’s short. :)
I love the premise. Dr. Watts bet himself that he could write a book where god exists and make it all sound sane.
Love the autistic chick. She’s what lemmings think they are when they call themselves autistic, but she’s far along the spectrum. Her story is absolutely heartbreaking.
Loved Valerie the vampire as well. Watts did a great job fleshing out the vampire thing in general and with the character herself. Only thing that hit me wrong was how they broke out of the lab. The plan was supposed to read as pure logic, but it was bordering on supernatural senses and intelligence to my mind. But what do I know? I’m a mere baseline. :(
I can see myself in Brooks. An aging guy trying to keep up with a radically evolving world. Wonder if that character was Watts himself in some ways.